压气机叶片叶根轮槽物理场预测及快速优化设计  

Physical Field Prediction and Fast Optimization Design of Compressor Blade Roots and Grooves

作　　者：赵宇轩 陈子峰 黄丞明 谢永慧[1] 张荻[1] ZHAO Yuxuan;CHEN Zifeng;HUANG Chengming;XIE Yonghui;ZHANG Di(School of Energy and Power Engineering,Xi’an Jiaotong University,Xi’an 710049,China)

机构地区：[1]西安交通大学能源与动力工程学院,西安710049

出　　处：《西安交通大学学报》2024年第4期96-106,共11页Journal of Xi'an Jiaotong University

基　　金：国家科技重大专项资助项目(J2019-Ⅳ-0022-0090);中央高校基本科研业务费专项资金资助项目(xtr072021002)。

摘　　要：为获得压气机叶片叶根轮槽区域的物理场分布状况、降低其型线优化的时间成本,提出一种叶根轮槽物理场预测模型及快速优化设计方法。选取叶根轮槽的关键几何参数作为设计变量和状态变量,建立了参数化模型;基于深度图卷积神经网络,构建了叶根轮槽区域物理场快速预测模型,通过对比有限元分析结果验证了模型的预测精度;基于预测模型和遗传算法,进行了叶根轮槽型线的快速优化设计。结果表明:利用所提预测模型对单个设计工况的分析相比于有限元分析的加速效果达到103量级,位移和应力预测值的变化趋势与有限元分析值的变化趋势一致,最大总位移的相对预测偏差在±1%范围附近,最大等效应力相对预测偏差在±5%范围内;优化后压气机叶片叶根轮槽的最大等效应力由240.96 MPa降低至206.37 MPa,减小了14.36%,优化效果明显。To obtain the physical field distribution of the blade root and groove region of the compressor and reduce the time cost of profile optimization,a physical field prediction model for blade roots and grooves and a fast optimization design method are proposed.The key geometric parameters of blade roots and grooves are selected as both design and state variables,and a parametric model is established.Based on the deep graph convolutional network,a fast prediction model for the physical field in the blade root and groove region is constructed,and the prediction accuracy of the model is verified through the comparison of finite element analysis results.Based on the prediction model and genetic algorithm,the fast optimization design of the profile is conducted.The results show that compared with the finite element analysis,the acceleration effect of the prediction model for a single design condition can reach 103 orders of magnitude.The variation trend of the predicted displacement and stress is consistent with that of the finite element analysis.The relative prediction deviation of the maximum total displacement is approximately±1%,and the relative prediction deviation of the maximum von Mises equivalent stress is within±5%.The maximum von Mises equivalent stress value of the optimized compressor blade root and groove is reduced from 240.96 MPa to 206.37 MPa,with a reduction rate of 14.36%.The optimization effect is remarkable.

关 键 词：压气机 叶根轮槽 深度学习 物理场预测 

分 类 号：TK05[动力工程及工程热物理]